Particle Swarm Optimization Ear Identification System

Biometric identification methods are proved to be very useful, natural, and easy for users than conventional methods of human identification. Ear biometric is used for personal identification and verification. Ear recognition is the most prominent ongoing biometric research. Ear image has rich edges due to intricate curves. Therefore, in this work, edges are revealed using a canny edge detector. In this paper, a simple and fast algorithm is developed for ear matching, which is based on Particle Swarm Optimization (PSO). The PSO method is exploited to match ear images with other ear images in the database. In-ear matching, the AMI EAR database is used, and the result shows that the accuracy of proposed method was 98% for testing 50 images and 96.6% when testing 150 images which surpasses other benchmark methods, namely Principal Component Analysis (PCA) and Scale Invariant Feature Transform (SIFT).

[1]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[2]  M. Arunkumar.  PALMPRINT AND FACE BASED MULTIMODAL RECOGNITION USING PSO DEPENDENT FEATURE LEVEL FUSION , 2013 .

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Hanaa S. Ali,et al.  Boosted Decision Trees for Vertebral Column Disease Diagnosis , 2014, SOFA.

[5]  Mark S. Nixon,et al.  Force field feature extraction for ear biometrics , 2005, Comput. Vis. Image Underst..

[6]  Alma Y. Alanis,et al.  Image Classification Using PSO-SVM and an RGB-D Sensor , 2014 .

[7]  Ahmad Taher Azar,et al.  Linguistic Hedges Fuzzy Feature Selection for Differential Diagnosis of Erythemato-Squamous Diseases , 2012, SOFA.

[8]  Ajay Kumar,et al.  Robust ear identification using sparse representation of local texture descriptors , 2013, Pattern Recognit..

[9]  Chenye Wu,et al.  Automated human identification using ear imaging , 2012, Pattern Recognit..

[10]  Jihen Malek,et al.  Adaptive noise-reducing anisotropic diffusion filter , 2015, Neural Computing and Applications.

[11]  Fadi N. Sibai,et al.  Ear recognition with feed-forward artificial neural networks , 2012, Neural Computing and Applications.

[12]  S. Ramachandran,et al.  Entropy-cum-Hough-transform-based ear detection using ellipsoid particle swarm optimization , 2015, Machine Vision and Applications.

[13]  Ma Chi,et al.  Ear Recognition Based on Forstner and SIFT , 2013 .

[14]  Arun Ross,et al.  Towards understanding the symmetry of human ears: A biometric perspective , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[15]  Akhtar Hussain,et al.  A Novel Ear Identification System for Security Applications , 2013 .

[16]  Kareem Kamal A. Ghany,et al.  Human Ear Recognition Using Geometrical Features Extraction , 2015 .

[17]  M. Usman Akram,et al.  Personal Identification Using Ear Recognition , 2012 .

[18]  Rerkchai Fooprateepsiri,et al.  An Efficient Features Ear Based Personal Identification Approach Forensic Science Tasks , 2011 .

[19]  Rabie A. Ramadan,et al.  A Fuzzy Approach of Sensitivity for Multiple Colonies on Ant Colony Optimization , 2016, SOFA.

[20]  Abdenour Hadid,et al.  Ear biometric recognition using local texture descriptors , 2014, J. Electronic Imaging.

[21]  B. K. Shreyamsha Kumar,et al.  Image denoising based on gaussian/bilateral filter and its method noise thresholding , 2013, Signal Image Video Process..

[22]  Jihen Malek,et al.  NEW TRENDS IN DATA PRE-PROCESSING METHODS FOR SIGNAL AND IMAGE CLASSIFICATION Noise-estimation-based anisotropic diffusion approach for retinal blood vessel segmentation , 2022 .

[23]  Ajay Kumar,et al.  Reliable ear identification using 2-D quadrature filters , 2012, Pattern Recognit. Lett..

[24]  Peng-Yeng Yin,et al.  Particle swarm optimization for point pattern matching , 2006, J. Vis. Commun. Image Represent..

[25]  Yin Guo,et al.  3D Ear Recognition Using SIFT Keypoint Matching , 2011 .

[26]  Ahmad Taher Azar,et al.  Optimistic Multi-granulation Rough Set-Based Classification for Neonatal Jaundice Diagnosis , 2014, SOFA.